Mailing List Archives

Public Access

 		[Computer Systems Lab]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Condor-users] MPICH2 wrapper script (mpich2script) for parallel universe

Hi Senthil,

I'll forward you my copy of mpd.py offline.

Regards,
Mark

Natarajan, Senthil wrote:

Hi Mark,
Thanks for letting me know the fix, I appreciate.
I did add those three lines and updated mpd.conf
file(MPD_PORT_RANGE=50001:59999). please find the modified mpd.py. Looks
like I didn't properly added seems. I am getting this error. 
mpdboot_machine2 (handle_mpd_output 388): from mpd on machine1, invalid
port info:


mpdboot error : 255

Could you please let me know, is mpd.py has correct fix for port range.
Thanks,
Senthil
-----Original Message-----
From: condor-users-bounces@xxxxxxxxxxx
[mailto:condor-users-bounces@xxxxxxxxxxx] On Behalf Of Mark Calleja
Sent: Tuesday, April 03, 2007 3:21 AM
To: Condor-Users Mail List
Subject: Re: [Condor-users] MPICH2 wrapper script (mpich2script) for
parallel universe

Hi Senthil,
The fix for this was provided by Ralph Butler at MTSU. It involves editing mpd.py and adding three lines, so a diff between the new and original files gives (using v1.0.5p3 of MPICH2): 

141d140
<                                  'MPD_PORT_RANGE'       :  0,
150,151d148
<         if self.parmdb['MPD_PORT_RANGE']:
<             os.environ['MPICH_PORT_RANGE'] =
self.parmdb['MPD_PORT_RANGE']
After making this change, you will want to add the following in your ~/.mpd.conf file on all hosts: 

MPD_PORT_RANGE=50001:59999

This works in my tests.

Regards,
Mark

Natarajan, Senthil wrote:

Hi Mark,
Thanks for your mp2script.

I was wondering do you know how to set the port range for mpd to start
on other machines.

In your script I added this,
export MPICH_PORT_RANGE=50001:59999

so the local mpd starts in the specified port range, but the mpd

started

through mpdboot on remote machines are using random ports. How to

start

the remote mpd also in the above specified port range. Because of the
random port number the firewall blocks the connection.

Thanks,
Senthil



-----Original Message-----
From: condor-users-bounces@xxxxxxxxxxx
[mailto:condor-users-bounces@xxxxxxxxxxx] On Behalf Of Mark Calleja
Sent: Wednesday, March 28, 2007 4:49 AM
To: Condor-Users Mail List
Subject: Re: [Condor-users] MPICH2 wrapper script (mpich2script) for
parallel universe

Hi Nkwebi,
I've modified my version of mp2script which now works with the "cpi" example code that MPICH2 builds when run over multiple SMP machines. Fancy testing it and reporting any feedback? One thing to note: there seems to be a bug with the current version of MPICH2 (v1.0.5p3), at least certainly when using the ch3:nemesis device, maybe even the ch3:ssm. The fix requires changing the following line in mpiexec.py
(at 
around line 789):

Change this line:
    msgToMPD['ifhns'][loRange] = ifhn
to this:
    if ifhn:  msgToMPD['ifhns'][loRange] = ifhn
Thanks to Ralph Butler at MTSU for pointing this out, without which I couldn't get mp2script to work. 

Cheers,
Mark


Nkwebi Peace Motlogelwa wrote:

Thanks Mark for the script...I just tried it and it works fine if the



parallel program is  executed on a single dedicated node.. The script
starts mpd on the master node (rank==0 or $_CONDOR_PROCNO ==0) only, and if one has many dedicated execute nodes, the script does not 
start

mpd on the other nodes.. Will try to modify it to get it to start mpd
on all dedicated execute nodes..so far tried using mpdboot, but it seems not as straight forward to get the ring of mpd's working.. 

regards..
On 3/16/07, *Mark Calleja* <M.Calleja@xxxxxxxxxxxxxxx <mailto:M.Calleja@xxxxxxxxxxxxxxx>> wrote: 

    Hi Nkwebi,

    I don't know if you still need this, but you can get my copy of
    mp2script at:

    http://www.escience.cam.ac.uk/~mcal00/condor/mp2script.asc
    <http://www.escience.cam.ac.uk/%7Emcal00/condor/mp2script.asc>

    Copy and paste it, and rename it as mp2script. A couple of points

you

    should bear in mind: I had to put a .mpd.conf file in the home
    directory
    of the user running condor (I use dedicated condor user

accounts),

    but I
    also had to set the env var MPD_CONF_FILE in the script,

otherwise

mpd

    failed to find the file. I also load LD_LIBRARY_PATH with the

compiler

    libs I used to build mpich2 (I used ifort/icc 9.1). This script

works

    fine with the "cpi" example that gets built by mpich2 in
    /path/to/mpich2/distro/examples.

    Cheers,
    Mark

    Nkwebi Peace Motlogelwa wrote:
    > Hi all... I need a working MPICH2 wrapper script for condor's
    > parallel universe...I use condor-6.8.4, but it comes with

wrapper

    > scripts for LAM and MPICH1 only.. I tried to modify the
    > mpich1script, but not winning so far... anybody using condor
    > and mpich2 and willing to share their wrapper scripts?...Pls

help..

    _______________________________________________
    Condor-users mailing list
    To unsubscribe, send a message to

condor-users-request@xxxxxxxxxxx

    <mailto:condor-users-request@xxxxxxxxxxx> with a
    subject: Unsubscribe
    You can also unsubscribe by visiting
    https://lists.cs.wisc.edu/mailman/listinfo/condor-users

    The archives can be found at either
    https://lists.cs.wisc.edu/archive/condor-users/


http://www.opencondor.org/spaces/viewmailarchive.action?key=CONDOR



------------------------------------------------------------------------

_______________________________________________
Condor-users mailing list
To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx

with a

subject: Unsubscribe
You can also unsubscribe by visiting
https://lists.cs.wisc.edu/mailman/listinfo/condor-users

The archives can be found at either
https://lists.cs.wisc.edu/archive/condor-users/
http://www.opencondor.org/spaces/viewmailarchive.action?key=CONDOR

_______________________________________________
Condor-users mailing list
To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx

with

a
subject: Unsubscribe
You can also unsubscribe by visiting
https://lists.cs.wisc.edu/mailman/listinfo/condor-users

The archives can be found at either
https://lists.cs.wisc.edu/archive/condor-users/
http://www.opencondor.org/spaces/viewmailarchive.action?key=CONDOR

_______________________________________________
Condor-users mailing list
To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx

with a

subject: Unsubscribe
You can also unsubscribe by visiting
https://lists.cs.wisc.edu/mailman/listinfo/condor-users

The archives can be found at either
https://lists.cs.wisc.edu/archive/condor-users/
http://www.opencondor.org/spaces/viewmailarchive.action?key=CONDOR


_______________________________________________
Condor-users mailing list
To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx with
a
subject: Unsubscribe
You can also unsubscribe by visiting
https://lists.cs.wisc.edu/mailman/listinfo/condor-users

The archives can be found at either
https://lists.cs.wisc.edu/archive/condor-users/
http://www.opencondor.org/spaces/viewmailarchive.action?key=CONDOR
------------------------------------------------------------------------ 

_______________________________________________
Condor-users mailing list
To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx with a
subject: Unsubscribe
You can also unsubscribe by visiting
https://lists.cs.wisc.edu/mailman/listinfo/condor-users

The archives can be found at either
https://lists.cs.wisc.edu/archive/condor-users/
http://www.opencondor.org/spaces/viewmailarchive.action?key=CONDOR



--
Dr Mark Calleja
Cambridge eScience Centre, University of Cambridge
Centre for Mathematical Sciences, Wilberforce Road, Cambridge CB3 0WA
Tel. (+44/0) 1223 765317, Fax  (+44/0) 1223 765900
http://www.escience.cam.ac.uk/~mcal00